-
[Qwen models provide methods to deploy local API based on OpenAI API](https://github.com/QwenLM/Qwen), please add support for it.
We tried add a new provider, and input our local api in "Provider URL…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
训练框架为**LLaMA-Factory-0.7.0**
```shell
export NCCL_DEBUG=INFO
export NCCL_IB_DISABLE=0
export NCCL_…
-
**问题描述 / Problem Description**
运行streamlit run webui.py后生成的external url,port为默认的本机Ip:8501,外部浏览器无法访问。
**复现问题的步骤 / Steps to Reproduce**
我按照文档流程三步走:
1. 运行本机fastchat服务: python server/llm_api.py
![I…
rabum updated
2 months ago
-
**问题描述 / Problem Description**
知识库问答,出现API通信错误,检索条目3变成1条也出错
**复现问题的步骤 / Steps to Reproduce**
1. 执行 '$ python startup.py -a'
2. 点击 '知识库问答'
3. 输入问题
4. 问题出现 / Problem occurs
**预期的结果 / Expected…
-
You can play with the space & retrieval models here: https://b3246e5ab28482f60e.gradio.live - Not all models & indices are cached yet so some first runs may be slow but once cached it should be blazin…
-
### Your current environment
The output of `python collect_env.py`
```text
root@newllm201:/workspace# vim collect.py
root@newllm201:/workspace# python3 collect.py
Collecting environment info…
-
### Documentation Issue Description
Openllm cannot be utilized.
code:
from vllm.model_executor.parallel_utils.parallel_state import destroy_model_parallel
destroy_model_parallel()
llm = …
-
**问题描述 / Problem Description**
Qwen-14B-Chat对话速度很慢,比我直接用fastchat生成api的对话要慢很多,目测大概差了10倍以上。
我已经设置了4张显卡全部启动,都没有装flash-attention。
用fastchat的时候,启动方式是:
python3 -m fastchat.serve.controller
python3 -m f…
-
#### Describe the bug
#### Setup and configuration
**Current version**:
(opendevin) taozhiyu@603e5f4a42f1 OpenDevin-main % git log -n 1
fatal: not a git repository (or any of the parent di…
-
**问题描述 / Problem Description**
使用在线embedding模型时,说类没有can_embedding这个方法,但是确实是有的,直接导入就是正常的
![51df7835dedc66f36d114c65733d67c](https://github.com/chatchat-space/Langchain-Chatchat/assets/33566026/470f6c…